Suggested queries — how the suggest engine works

You can write your own monitored questions from scratch, but most people want a starting set. Refresh ideas in the Questions page calls the suggest engine and proposes 10–15 buyer-style queries calibrated to what your site actually says it does. This article explains where those queries come from.

Two grounding modes

A suggested query can be one of two kinds:

• Grounded in your pages. The engine read your homepage plus any stored Content Audit pages (about, pricing, docs, features…) and used a real understanding of your product to write the question. These are tailored to you and tend to surface signals unique to your positioning.
• Category preset fallback. When we don't have enough page data to ground a query, we draw from a library of 13 preset categories and emit one of the canonical buyer questions for the category that most closely matches your domain.

Each suggestion in the dialog carries a small provenance badge showing which mode produced it. Look at the badges to gauge how much each query is custom-fit vs. category baseline.

The 13 preset categories

When the engine falls back to category presets, it picks one of:

Category	Examples of products it covers
deployment_hosting	Vercel, Netlify, Render, Fly.io, Railway, Northflank
analytics	Mixpanel, Amplitude, PostHog, Plausible
crm	HubSpot, Pipedrive, Close, Salesforce
helpdesk_support	Intercom, Zendesk, Front, Help Scout
email_outreach	Resend, Postmark, SendGrid, Customer.io
project_management	Linear, Asana, Jira, ClickUp
collaboration_docs	Notion, Confluence, Coda
payments_billing	Stripe, Lemon Squeezy, Paddle
design_prototyping	Figma, Framer, Penpot
security_monitoring	Sentry, Datadog, Honeybadger, BetterStack
developer_tools	Cursor, GitHub Copilot, JetBrains AI, Linear
automation_workflow	Zapier, n8n, Make, Pipedream
generic_saas	Anything that doesn't fit the others — last-resort fallback

Categories are deliberately narrow — narrower categories produce sharper questions. If your domain straddles two (e.g. a CRM with strong analytics features), the engine picks one and labels it; you can re-run Refresh ideas to bias toward another category by re-scraping with a different page emphasis.

How "grounded" actually works

When you have stored Content Audit pages (the weekly cron has run at least once), the suggest engine builds a Domain Understanding Profile from:

• The homepage hero text and meta description.
• The <title> + meta description of every audited page (about, pricing, docs, features…).
• The Discovery Readiness signals (which pages have JSON-LD, what schema types, what the canonical URLs look like).

This goes into the LLM prompt as ground truth so the model can write questions that reflect what your product actually does — not what its category usually does. Grounded suggestions tend to:

• Use specific feature words from your pages ("preview deployments", "instant rollback", "edge functions") rather than generic category vocabulary.
• Phrase the buyer intent in ways that match what your hero copy promises.
• Cover use cases that show up in your /docs or /features pages rather than asking generic "best X" questions.

Provenance warning when grounding fails

If the engine has no page data — fresh domain, homepage scrape failed, no Content Audit yet — it falls back to category presets and the dialog surfaces a banner explaining why:

• "We couldn't reach your homepage to read positioning context. Suggestions below are generic category questions; re-run after the homepage is reachable for tailored ones."
• "No Content Audit pages stored yet. Once the weekly audit runs Monday 04:00 UTC, suggested queries will use your pricing, about, and docs pages as additional context."

Click Refresh ideas again after the underlying issue is fixed to get the grounded version. The dialog is non-destructive — your existing monitored questions stay put.

Quality badges per suggestion

Inside the dialog, each suggested query has a quality badge:

• High — multi-source grounding (homepage + ≥3 page audits) + preset boost. These are the most likely to surface real signal.
• Medium — grounded but with limited page coverage, OR strong preset match without page data. Worth keeping but verify the framing matches your actual positioning.
• Low — preset-only fallback. Useful as a starting point but consider rewriting in your own words before tracking.

What happens when you click "Add to monitored"

Each query you add becomes a row in the queries table with:

• Cadence default: daily_pulse (you can change it later).
• Engines: whatever your tier provides.
• Source tag indicating it came from suggest, not manual entry — used for analytics on which suggested queries actually move the needle.

The first scan against the new query runs at the next daily pulse (or immediately if you click Run scan with it selected).

Honest limits

Read further

• Manual, pulse, and deep scans — what runs on each query you add to monitored.
• Content audit — the source of the multi-page grounding data.
• Mention vs. citation — what the suggested queries are actually measuring.